© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4349
    Prev
    Next
    INDEX
    Explanations

    creative works, study, or depiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тную
    -0.95
     berjudul
    -0.88
    🔥🔥
    -0.85
     mulut
    -0.85
     jangan
    -0.82
    -0.81
    わせる
    -0.81
    εύ
    -0.81
    sbereich
    -0.81
     penuh
    -0.80
    POSITIVE LOGITS
     exploration
    1.70
     celebration
    1.61
     study
    1.52
     tribute
    1.52
     examination
    1.49
     homage
    1.45
     representation
    1.42
     treatise
    1.38
     attempt
    1.38
     portrait
    1.34
    Activations Density 0.074%

    No Known Activations